CN105104291A - Dairy cow motion state judging method and corresponding intelligent feeding method - Google Patents
Dairy cow motion state judging method and corresponding intelligent feeding method Download PDFInfo
- Publication number
- CN105104291A CN105104291A CN201510445489.8A CN201510445489A CN105104291A CN 105104291 A CN105104291 A CN 105104291A CN 201510445489 A CN201510445489 A CN 201510445489A CN 105104291 A CN105104291 A CN 105104291A
- Authority
- CN
- China
- Prior art keywords
- milk cow
- state
- running
- motion state
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 235000013365 dairy product Nutrition 0.000 title abstract description 12
- 239000008267 milk Substances 0.000 claims abstract description 132
- 235000013336 milk Nutrition 0.000 claims abstract description 132
- 210000004080 milk Anatomy 0.000 claims abstract description 132
- 230000001133 acceleration Effects 0.000 claims description 44
- 238000005315 distribution function Methods 0.000 claims description 13
- 230000035611 feeding Effects 0.000 description 28
- 238000009395 breeding Methods 0.000 description 4
- 230000001488 breeding effect Effects 0.000 description 4
- 244000144972 livestock Species 0.000 description 4
- 230000003862 health status Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K67/00—Rearing or breeding animals, not otherwise provided for; New or modified breeds of animals
- A01K67/02—Breeding vertebrates
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Environmental Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Dentistry (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Zoology (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Physiology (AREA)
- Dairy Products (AREA)
Abstract
The invention relates to a dairy cow motion state judging method and a corresponding intelligent feeding method. The dairy cow motion state judging method comprises the following steps: 1) acquiring a plurality of groups of accelerated speed data in a dairy cow forward direction within a set period; 2) calculating a forward difference sequence d of an accelerated speed zero-mean-value sequence for each group of accelerated speed data; 3) calculating one or more of standard deviation a, range b and kurtosis c of the forward difference sequence d; 4) judging the motion state of a dairy cow by virtue of the calculated data and a corresponding threshold value, judging that the dairy cow within the period is in a running state when the calculated data is greater than or equal to the threshold value, and judging that the dairy cow within the period is in the running state when the calculated data is smaller than the threshold value; 5) integrating the motion state, corresponding to each group of accelerated speed data, of the diary cow to calculate a proportion of the period that the diary cow is in the running state to the total time, and determine feeding amount of the diary cow. According to the dairy cow motion state judging method, each dairy cow is guaranteed to have proper feeding amount, so that automatic feeding of the dairy cow is realized, and the milk producing level of the dairy cow is improved.
Description
Technical field
The invention belongs to livestock breeding intelligent management field, be specifically related to the intelligent feeding method of a kind of milk cow motion state method of discrimination and correspondence.
Background technology
As everyone knows, dairy has become column support type enterprise in China's livestock breeding, and its development determines the economic level of China's livestock breeding, affects the health status of China its people.Along with the emergence of China's livestock breeding, the demand of milk is increased, therefore need the diet ensureing every cow head, ensure the milk yield of milk cow.
At present, the feeding method of milk cow manually unifies feeding, not only cause a large amount of wastes of human resources, operating efficiency is low, and, because the mass motion level of every cow head is different, its feed demand is also different, if every cow head all adopts identical feeding amount to carry out feeding, is easy to occur the waste of feed or the situation of deficiency, affect the health status of milk cow, make the level of giving milk of milk cow unbalanced.
Summary of the invention
The object of this invention is to provide the intelligent feeding method of a kind of milk cow motion state method of discrimination and correspondence, the milk cow feeding method of the prior art in order to solve causes the unbalanced problem of level of giving milk of milk cow.
For achieving the above object, the solution of the present invention comprises:
A kind of milk cow motion state method of discrimination, comprises the following steps:
1) acceleration of milk cow direction of advance in the setting-up time cycle is gathered;
2) the forward difference sequence d of acceleration zero-mean sequence is calculated;
3) what calculate in three parameters---standard deviation a, extreme difference b, kurtosis c---of forward difference sequence d is one or more;
4) pass through the motion state of the threshold decision milk cow of data and the correspondence calculated, when the data calculated are more than or equal to the threshold value of its correspondence time, judge that in this cycle, milk cow is in the state of running; When the data calculated are less than the threshold value of its correspondence time, judge that in this cycle, milk cow is in the state of running.
Described step 3) in, calculate described plural parameter, to each parameter, judge the motion state of milk cow according to the threshold values of correspondence, then the motion state of the logic rules comprehensive descision milk cow of foundation setting.
Described step 4) in, data according to calculating set up basic reliability distribution function, wherein, m (1), m (2) represent that milk cow is in walking states and the basic reliability distribution of state of running respectively, and m (Θ) represents uncertain basic reliability distribution; Corresponding basic reliability distribution value F is drawn by the threshold value of its correspondence; When step 3) data that calculate are when being 1, if the m of basic reliability distribution value F is (1) – m (2) > ε
1, m (Θ) < ε
2, can walking states be judged as; If m is (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as; When step 3) data that calculate are when being more than 2 or 2, XOR carried out to the basic reliability distribution value F obtained and obtain belief assignment value F
xif, belief assignment value F
xm (1) – m (2) > ε
1, m (Θ) < ε
2, can walking states be judged as; If m is (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as.
A kind of milk cow intelligence feeding method, comprises the following steps:
1) within a period of time, gather some groups of acceleration informations, often organize the acceleration information that acceleration information is the milk cow direction of advance in setting-up time cycle;
2) for often organizing acceleration information, the forward difference sequence d of acceleration zero-mean sequence is calculated;
3) what calculate in the standard deviation a of forward difference sequence d, extreme difference b, kurtosis c is one or more;
4) pass through the motion state of the threshold decision milk cow of data and the correspondence calculated, when the data calculated are more than or equal to the threshold value of its correspondence time, judge that in this cycle, milk cow is in the state of running; When the data calculated are less than the threshold value of its correspondence time, judge that in this cycle, milk cow is in the state of running;
5) comprehensively by the motion state of milk cow corresponding to each group of acceleration information, calculate the ratio that cycle that milk cow is in the state of running accounts for total time, determine the feeding amount of milk cow.
Described step 3) in, calculate described plural parameter, to each parameter, judge the motion state of milk cow according to the threshold values of correspondence, then the motion state of the logic rules comprehensive descision milk cow of foundation setting.
Described step 4) in, data according to calculating set up basic reliability distribution function, wherein, m (1), m (2) represent that milk cow is in walking states and the basic reliability distribution of state of running respectively, and m (Θ) represents uncertain basic reliability distribution; Corresponding basic reliability distribution value F is drawn by the threshold value of its correspondence; When step 3) data that calculate are when being 1, if the m of basic reliability distribution value F is (1) – m (2) > ε
1, m (Θ) < ε
2, can walking states be judged as; If m is (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as; When step 3) data that calculate are when being more than 2 or 2, XOR carried out to the basic reliability distribution value F obtained and obtain belief assignment value F
xif, belief assignment value F
xm (1) – m (2) > ε
1, m (Θ) < ε
2, can walking states be judged as; If m is (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as.
Described step 5) in determine that the mode of the feeding amount of milk cow is: the cycle being in the state of running according to milk cow accounts for the ratio of total time, milk cow amount of exercise is divided into acrokinesia, proper motion, the very few three kinds of amounts of exercise of motion; The feeding amount of milk cow is determined by amount of exercise.
The invention has the beneficial effects as follows: within a period of time, gather some groups of acceleration informations, calculate the standard deviation of corresponding forward difference sequence d, extreme difference, kurtosis value one or more, by calculate data and correspondence threshold decision its be in ambulatory status or state of running, then account for the ratio of total time according to the cycle of state of running, determine the feeding amount of milk cow, ensure that every cow head has suitable feeding amount, achieve the automatic feeding of milk cow, improve the level of giving milk of milk cow.
Accompanying drawing explanation
Fig. 1 is the flow chart of milk cow motion state method of discrimination embodiment 3 of the present invention;
Fig. 2 is the flow chart of milk cow of the present invention intelligence feeding method embodiment
Embodiment
Milk cow motion state method of discrimination embodiment 1
The milk cow motion state method of discrimination of the present embodiment comprises the following steps:
1) acceleration of milk cow direction of advance in the setting-up time cycle is gathered.
The acceleration of milk cow direction of advance at least one setting-up time cycle is gathered by acceleration transducer.
2) the forward difference sequence d of acceleration zero-mean sequence is calculated.
If acceleration sequence is Z=[z
1, z
2..., z
n], calculate the average z '=(z of z
1+ z
2+ ... + z
n)/n, each element that will speed up in degree series Z deducts average z ', obtains new zero-mean sequence Z ", sequence Z " is carried out to forward difference, obtains sequence d.
3) standard deviation of forward difference sequence d is calculated.
Calculate the standard deviation of forward difference sequence d, and its numerical value is designated as a.
4) motion state of the threshold decision milk cow of data and the correspondence calculated is passed through.
The threshold value arranging standard deviation a is 2, when standard deviation a >=2, judges that milk cow is in the state of running; As standard deviation a<2, judge that milk cow is in walking states.
In the above-described embodiments, calculate the standard deviation of forward difference sequence d, in other embodiments, extreme difference b or the kurtosis c of forward difference sequence d can be calculated.
In the above-described embodiments, the threshold value of described standard deviation a is 2, and as other embodiments, its threshold values can be 1.8 other numerical value such as grade.
Milk cow motion state method of discrimination embodiment 2
In milk cow motion state method of discrimination embodiment 1, described step 3) in: the standard deviation calculating forward difference sequence d is a, and extreme difference is b.
4) calculate described plural parameter, to each parameter, judge the motion state of milk cow according to the threshold values of correspondence, then the motion state of the logic rules comprehensive descision milk cow of foundation setting.
Judge the motion state of milk cow respectively according to the threshold value 2 of standard deviation a, the extreme difference threshold value 7 that is b, the setting milk cow state of running is logical value " 1 ", and walking states is logical value " 0 "; Logic and operation is done to judged result, when logic and operation Output rusults is " 1 ", judges that milk cow is in the state of running; When logical operation Output rusults is " 0 ", judge that milk cow is in walking states.Above-mentioned logical operation rule also can be or other logical operation rule such as computing.
In the above-described embodiments, described extreme difference is the threshold value of b is 7, and as other embodiments, its threshold values can be 6.8 other numerical value such as grade.
In the above-described embodiments, calculate standard deviation and the extreme difference of forward difference sequence d, as other embodiments, standard deviation and the kurtosis of forward difference sequence d can be calculated, or extreme difference and kurtosis.
In the above-described embodiments, calculate standard deviation and the extreme difference of forward difference sequence d, as other embodiments, the standard deviation of forward difference sequence d, extreme difference and kurtosis can be calculated, its judgment mode is identical with the judgment mode of embodiment 2, therefore not at this repeated description.
Milk cow motion state method of discrimination embodiment 3
As shown in Figure 1, the milk cow motion state method of discrimination of the present embodiment comprises the following steps:
1) acceleration of milk cow direction of advance in the setting-up time cycle is gathered.
The acceleration of milk cow direction of advance at least one time cycle is gathered by acceleration transducer.
2) the forward difference sequence d of acceleration zero-mean sequence is calculated.
If acceleration sequence is Z=[z
1, z
2..., z
n], calculate the average z '=(z of z
1+ z
2+ ... + z
n)/n, each element that will speed up in degree series Z deducts average z ', obtains new zero-mean sequence Z ", sequence Z " is carried out to forward difference, obtains sequence d.
3) standard deviation, extreme difference, the kurtosis of forward difference sequence d is calculated.
Calculate standard deviation, extreme difference, the kurtosis of forward difference sequence d, standard deviation is designated as a, extreme difference is designated as b, kurtosis is designated as c.
4) basic reliability distribution function is set up to standard deviation, extreme difference, kurtosis, and standard deviation, extreme difference, kurtosis are substituted into basic reliability distribution function, judge the motion state of milk cow.
M (1), m (2) represent that milk cow is in walking states and the basic reliability distribution of state of running respectively, and m (Θ) represents uncertain basic reliability distribution.Process of establishing is as follows:
Standard deviation:
If a<1, then m (1)=0.9, m (2)=0, m (Θ)=0.1;
If 1≤a<2, then m (1)=(Θ)=0.1, [1 – (a – 1)] × 0.9, m (2)=[a – 1] × 0.9, m;
If a >=2, then m (1)=0, m (2)=0.9, m (Θ)=0.1.
Extreme difference:
If b<5, then m (1)=0.9, m (2)=0, m (Θ)=0.1;
If 5≤b<7, then m (1)=[1 – (b – 5)/2] × 0.9, m (2)=[(b – 5)/2] × 0.9, m (Θ)=0.1;
If b >=7, then m (1)=0, m (2)=0.9, m (Θ)=0.1.
Kurtosis:
If c<2, then m (1)=0.9, m (2)=0, m (Θ)=0.1;
If 2≤c<3, then m (1)=(Θ)=0.1, [1 – (c – 2)] × 0.9, m (2)=[c – 2] × 0.9, m;
If c >=3, then m (1)=0, m (2)=0.9, m (Θ)=0.1.
The standard deviation a of forward difference sequence d, extreme difference b, kurtosis c are substituted into corresponding basic reliability distribution function, calculate corresponding basic reliability distribution value F1, F2, F3, then F1, F2, F3 are substituted into formula (1), obtain belief assignment value F
x:
F
x=F1⊕F2⊕F3(1)
Choose thresholding ε
1=0.2, ε
2=0.03,
If belief assignment value F
xm (1) – m (2) > ε
1, m (Θ) < ε
2, can walking states be judged as;
M (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as.
In the above-described embodiments, described step 3) middle standard deviation, extreme difference, the kurtosis calculating forward difference sequence d.As other embodiments, described step 3) in only calculate the standard deviation of forward difference sequence d, extreme difference, kurtosis one of them.Basic reliability distribution function F is set up, m (1) – m (2) the > ε of F according to the data calculated
1, m (Θ) < ε
2, can walking states be judged as; If m is (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as.
In the above-described embodiments, described step 3) middle standard deviation, extreme difference, the kurtosis calculating forward difference sequence d.As other embodiments, described step 3) in only calculate the standard deviation of forward difference sequence d, extreme difference, kurtosis wherein two.Its determination methods is consistent with the determination methods in embodiment 3, therefore not at this repeated description.
In the above-described embodiments, described step 1) in the milk cow acceleration that gathers be the acceleration of milk cow three directions X, Y, Z.
Now according to instantiation, milk cow motion state method of discrimination embodiment 3 is specifically described.As shown in the table, be the milk cow acceleration information in two setting-up time cycles of stochastical sampling.
Bracket direction of advance is Z axis, is downwards X-axis along bracket, and vertical bracket is outwards Y-axis.When milk cow is in and walks or run state, its Z axis acceleration change is the most violent, therefore when differentiating milk cow state, chooses Z axis acceleration sequence as analytic target.
First, the average that can be calculated data group 1 is 1.0762, and the average of data group 2 is 1.2670, each element in Z axis acceleration sequence is deducted average, obtains zero-mean sequence, carries out forward difference, obtain sequence d to this zero-mean sequence.As shown in the table.
Calculate standard deviation, extreme difference, the kurtosis value of data group 1 and data group 2 sequence d respectively.Data group 1 be respectively 0.4721,2.04,2.7059, data group 2 be respectively 2.2775,9.07,2.3420.
The standard deviation of above-mentioned data group 1, extreme difference, kurtosis value are substituted into corresponding basic reliability distribution function, obtain: the basic reliability distribution value F1=[0.900.1] of data group 1, F2=[0.900.1], F3=[0.26470.63530.1], F1, F2, F3 are substituted into formula (1), obtains belief assignment value F
x=[0.98020.01710.0027], wherein m (1) – m (2)=0.9631> ε
1, m (Θ)=0.0027< ε
2, can judge that the milk cow of data group 1 is walking states;
The standard deviation of above-mentioned data group 2, extreme difference, kurtosis value are substituted into corresponding basic reliability distribution function, obtain: F1=[00.90.1], F2=[00.90.1], F3=[0.59220.30780.1] during the basic reliability distribution value of data group 2, F1, F2, F3 are substituted into formula (1), obtains belief assignment value F
x=[0.01430.98330.0024], wherein m (2) – m (1)=0.969> ε
1, m (Θ)=0.0024< ε
2, can judge that the milk cow of data group 2 is as the state of running.
Milk cow intelligence feeding method embodiment
Milk cow intelligence feeding method of the present invention determines the feeding amount of milk cow according to the motion state of milk cow, wherein the method for discrimination of milk cow motion state is identical with the milk cow motion state method of discrimination in above-described embodiment 1,2,3, therefore not in this repeat specification.
Choose exemplary embodiments to be below described milk cow intelligence feeding method embodiment of the present invention.
As shown in Figure 2, milk cow intelligence feeding method of the present invention comprises the following steps:
1) within a period of time, gather some groups of acceleration informations, often organize the acceleration information that acceleration information is the milk cow direction of advance of setting cycle.
Within a period of time, gathered the acceleration of at least one group of milk cow direction of advance by acceleration transducer.
2) for often organizing acceleration information, the forward difference sequence d of acceleration zero-mean sequence is calculated.
If wherein one group of acceleration sequence is x=[x
1, x
2..., x
n], calculate the average x '=(x of x
1+ x
2+ ... + x
n)/n, each element that will speed up in degree series x deducts average x ', obtains new zero-mean sequence x ", sequence x " is carried out to forward difference, obtains sequence d.
3) standard deviation, extreme difference, the kurtosis of forward difference sequence d is calculated.
Calculate standard deviation, extreme difference, the kurtosis of forward difference sequence d, standard deviation is designated as a, extreme difference is designated as b, kurtosis is designated as c.
4) basic reliability distribution function is set up to standard deviation, extreme difference, kurtosis; Standard deviation, extreme difference, kurtosis are substituted into basic reliability distribution function, judges the motion state of milk cow.
M (1), m (2) represent that milk cow is in walking states and the basic reliability distribution of state of running respectively, and m (Θ) represents uncertain basic reliability distribution.Process of establishing is as follows:
Standard deviation:
If a<1, then m (1)=0.9, m (2)=0, m (Θ)=0.1;
If 1≤a<2, then m (1)=(Θ)=0.1, [1 – (a – 1)] × 0.9, m (2)=[a – 1] × 0.9, m;
If a >=2, then m (1)=0, m (2)=0.9, m (Θ)=0.1.
Extreme difference:
If b<5, then m (1)=0.9, m (2)=0, m (Θ)=0.1;
If 5≤b<7, then m (1)=[1 – (b – 5)/2] × 0.9, m (2)=[(b – 5)/2] × 0.9, m (Θ)=0.1;
If b >=7, then m (1)=0, m (2)=0.9, m (Θ)=0.1.
Kurtosis:
If c<2, then m (1)=0.9, m (2)=0, m (Θ)=0.1;
If 2≤c<3, then m (1)=(Θ)=0.1, [1 – (c – 2)] × 0.9, m (2)=[c – 2] × 0.9, m;
If c >=3, then m (1)=0, m (2)=0.9, m (Θ)=0.1.
The standard deviation a of forward difference sequence d, extreme difference b, kurtosis c are substituted into corresponding basic reliability distribution function, calculate corresponding basic reliability distribution value F1, F2, F3, then F1, F2, F3 are substituted into formula (1), obtain belief assignment value F
x:
F
x=F1⊕F2⊕F3(1)
Choose thresholding ε
1=0.2, ε
2=0.03,
If belief assignment value F
xm (1) – m (2) > ε
1, m (Θ) < ε
2, can walking states be judged as; M (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as.
6) comprehensively by the motion state of milk cow corresponding to each group of acceleration information, calculate the ratio that cycle that milk cow is in the state of running accounts for total time, determine the feeding amount of milk cow.
The cycle being in the state of running according to milk cow accounts for the ratio of total time, determines the feeding amount of milk cow.
In the above-described embodiments, described step 1) in the milk cow acceleration that gathers be the acceleration of milk cow three directions X, Y, Z.
In the above-described embodiments, the cycle being in the state of running according to milk cow accounts for the ratio of total time, determines the feeding amount of milk cow.As other embodiments, the cycle being in the state of running according to milk cow accounts for the ratio of total time, milk cow amount of exercise is divided into acrokinesia, proper motion, the very few three kinds of amounts of exercise of motion, is determined the feeding amount of milk cow by this amount of exercise.
As, the amount of exercise of milk cow is divided into acrokinesia, proper motion, the very few three kinds of amounts of exercise of motion, wherein acrokinesia is cycle that milk cow is in the state of running account for the ratio of total time to be more than or equal to 3/5, proper motion is cycle that milk cow is in the state of running account for the ratio of total time to be less than 3/5, be more than or equal to 1/5, the very few cycle being in the state of running for milk cow of moving accounts for the ratio of total time and is less than 1/5.Gather 10 groups of data, judge that the cycle that milk cow is in the state of running accounts for total time ratio, when this ratio is more than or equal to 3/5, judge milk cow acrokinesia, therefore give maximum feedings; When this ratio is less than 3/5, when being more than or equal to 1/5, judging that milk cow motion is normal, give medium feeding.When ratio is less than 1/5, judges that milk cow motion is very few, therefore give minimum feeding.
Claims (7)
1. a milk cow motion state method of discrimination, is characterized in that: comprise the following steps:
1) acceleration of milk cow direction of advance in the setting-up time cycle is gathered;
2) the forward difference sequence d of acceleration zero-mean sequence is calculated;
3) what calculate in three parameters---standard deviation a, extreme difference b, kurtosis c---of forward difference sequence d is one or more;
4) pass through the motion state of the threshold decision milk cow of data and the correspondence calculated, when the data calculated are more than or equal to the threshold value of its correspondence time, judge that in this cycle, milk cow is in the state of running; When the data calculated are less than the threshold value of its correspondence time, judge that in this cycle, milk cow is in the state of running.
2. milk cow motion state method of discrimination according to claim 1, it is characterized in that: described step 3) in, calculate described plural parameter, to each parameter, the motion state of milk cow is judged according to the threshold values of correspondence, then the motion state of the logic rules comprehensive descision milk cow of foundation setting.
3. milk cow motion state method of discrimination according to claim 1, it is characterized in that: described step 4) in, data according to calculating set up basic reliability distribution function, wherein, m (1), m (2) represent that milk cow is in walking states and the basic reliability distribution of state of running respectively, and m (Θ) represents uncertain basic reliability distribution; Corresponding basic reliability distribution value F is drawn by the threshold value of its correspondence; When step 3) data that calculate are when being 1, if the m of basic reliability distribution value F is (1) – m (2) > ε
1, m (Θ) < ε
2, can walking states be judged as; If m is (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as; When step 3) data that calculate are when being more than 2 or 2, XOR carried out to the basic reliability distribution value F obtained and obtain belief assignment value F
xif, belief assignment value F
xm (1) – m (2) > ε
1, m (Θ) < ε
2, can walking states be judged as; If m is (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as.
4. a milk cow intelligence feeding method, is characterized in that: comprise the following steps:
1) within a period of time, gather some groups of acceleration informations, often organize the acceleration information that acceleration information is the milk cow direction of advance in setting-up time cycle;
2) for often organizing acceleration information, the forward difference sequence d of acceleration zero-mean sequence is calculated;
3) what calculate in the standard deviation a of forward difference sequence d, extreme difference b, kurtosis c is one or more;
4) pass through the motion state of the threshold decision milk cow of data and the correspondence calculated, when the data calculated are more than or equal to the threshold value of its correspondence time, judge that in this cycle, milk cow is in the state of running; When the data calculated are less than the threshold value of its correspondence time, judge that in this cycle, milk cow is in the state of running;
5) comprehensively by the motion state of milk cow corresponding to each group of acceleration information, calculate the ratio that cycle that milk cow is in the state of running accounts for total time, determine the feeding amount of milk cow.
5. milk cow intelligence feeding method according to claim 4, it is characterized in that: described step 3) in, calculate described plural parameter, to each parameter, the motion state of milk cow is judged according to the threshold values of correspondence, then the motion state of the logic rules comprehensive descision milk cow of foundation setting.
6. milk cow intelligence feeding method according to claim 4, it is characterized in that: described step 4) in, data according to calculating set up basic reliability distribution function, wherein, m (1), m (2) represent that milk cow is in walking states and the basic reliability distribution of state of running respectively, and m (Θ) represents uncertain basic reliability distribution; Corresponding basic reliability distribution value F is drawn by the threshold value of its correspondence; When step 3) data that calculate are when being 1, if the m of basic reliability distribution value F is (1) – m (2) > ε
1, m (Θ) < ε
2, can walking states be judged as; If m is (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as; When step 3) data that calculate are when being more than 2 or 2, XOR carried out to the basic reliability distribution value F obtained and obtain belief assignment value F
xif, belief assignment value F
xm (1) – m (2) > ε
1, m (Θ) < ε
2, can walking states be judged as; If m is (2) – m (1) > ε
1, m (Θ) < ε
2, can the state of running be judged as.
7. milk cow intelligence feeding method according to claim 4, it is characterized in that: described step 5) in determine that the mode of the feeding amount of milk cow is: the cycle being in the state of running according to milk cow accounts for the ratio of total time, milk cow amount of exercise is divided into acrokinesia, proper motion, the very few three kinds of amounts of exercise of motion; The feeding amount of milk cow is determined by amount of exercise.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510445489.8A CN105104291B (en) | 2015-07-27 | 2015-07-27 | A kind of milk cow motion state method of discrimination and corresponding intelligent feeding method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510445489.8A CN105104291B (en) | 2015-07-27 | 2015-07-27 | A kind of milk cow motion state method of discrimination and corresponding intelligent feeding method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105104291A true CN105104291A (en) | 2015-12-02 |
CN105104291B CN105104291B (en) | 2017-11-21 |
Family
ID=54652637
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510445489.8A Expired - Fee Related CN105104291B (en) | 2015-07-27 | 2015-07-27 | A kind of milk cow motion state method of discrimination and corresponding intelligent feeding method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105104291B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107027650A (en) * | 2017-03-21 | 2017-08-11 | 中国农业大学 | A kind of boar abnormal state detection method and device based on PSO SVM |
CN108814618A (en) * | 2018-04-27 | 2018-11-16 | 歌尔科技有限公司 | A kind of recognition methods of motion state, device and terminal device |
CN108990833A (en) * | 2018-09-11 | 2018-12-14 | 河南科技大学 | A kind of animal movement behavior method of discrimination and device based on location information |
CN109446931A (en) * | 2018-10-11 | 2019-03-08 | 河南科技大学 | Animal movement behavior method of discrimination and device based on sequential correlation analysis |
CN114258871A (en) * | 2021-11-22 | 2022-04-01 | 黑龙江省农业科学院畜牧兽医分院 | Pregnancy data monitoring device and method used in sheep breeding process |
CN116158374A (en) * | 2022-12-07 | 2023-05-26 | 杭州慧牧科技有限公司 | Intelligent poultry breeding method, device, computer equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010263953A (en) * | 2009-05-12 | 2010-11-25 | Oki Electric Ind Co Ltd | Motion analysis device, program and method thereof, and motion analysis system |
CN202255413U (en) * | 2011-08-31 | 2012-05-30 | 上海麦喀斯机械设备有限公司 | Dairy cow pedometer |
CN102973275A (en) * | 2012-11-14 | 2013-03-20 | 无锡智感星际科技有限公司 | Acquisition system and acquisition method of human motion state |
CN103340634A (en) * | 2013-06-17 | 2013-10-09 | 无锡市中安捷联科技有限公司 | Method for detecting human motion state based on accelerated speed changes |
CN103782954A (en) * | 2014-01-25 | 2014-05-14 | 广东燕塘乳业股份有限公司 | Cow fine breeding method based on RFID technology |
CN103892840A (en) * | 2014-03-06 | 2014-07-02 | 深圳市德凯瑞科技有限公司 | Intelligent wearing device and method for extracting human body motion features |
-
2015
- 2015-07-27 CN CN201510445489.8A patent/CN105104291B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010263953A (en) * | 2009-05-12 | 2010-11-25 | Oki Electric Ind Co Ltd | Motion analysis device, program and method thereof, and motion analysis system |
CN202255413U (en) * | 2011-08-31 | 2012-05-30 | 上海麦喀斯机械设备有限公司 | Dairy cow pedometer |
CN102973275A (en) * | 2012-11-14 | 2013-03-20 | 无锡智感星际科技有限公司 | Acquisition system and acquisition method of human motion state |
CN103340634A (en) * | 2013-06-17 | 2013-10-09 | 无锡市中安捷联科技有限公司 | Method for detecting human motion state based on accelerated speed changes |
CN103782954A (en) * | 2014-01-25 | 2014-05-14 | 广东燕塘乳业股份有限公司 | Cow fine breeding method based on RFID technology |
CN103892840A (en) * | 2014-03-06 | 2014-07-02 | 深圳市德凯瑞科技有限公司 | Intelligent wearing device and method for extracting human body motion features |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107027650A (en) * | 2017-03-21 | 2017-08-11 | 中国农业大学 | A kind of boar abnormal state detection method and device based on PSO SVM |
CN108814618A (en) * | 2018-04-27 | 2018-11-16 | 歌尔科技有限公司 | A kind of recognition methods of motion state, device and terminal device |
CN108814618B (en) * | 2018-04-27 | 2021-08-31 | 歌尔科技有限公司 | Motion state identification method and device and terminal equipment |
CN108990833A (en) * | 2018-09-11 | 2018-12-14 | 河南科技大学 | A kind of animal movement behavior method of discrimination and device based on location information |
CN109446931A (en) * | 2018-10-11 | 2019-03-08 | 河南科技大学 | Animal movement behavior method of discrimination and device based on sequential correlation analysis |
CN109446931B (en) * | 2018-10-11 | 2022-02-08 | 河南科技大学 | Animal movement behavior discrimination method and device based on time sequence correlation analysis |
CN114258871A (en) * | 2021-11-22 | 2022-04-01 | 黑龙江省农业科学院畜牧兽医分院 | Pregnancy data monitoring device and method used in sheep breeding process |
CN114258871B (en) * | 2021-11-22 | 2023-01-24 | 黑龙江省农业科学院畜牧兽医分院 | Pregnancy data monitoring device and method used in sheep breeding process |
CN116158374A (en) * | 2022-12-07 | 2023-05-26 | 杭州慧牧科技有限公司 | Intelligent poultry breeding method, device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN105104291B (en) | 2017-11-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105104291A (en) | Dairy cow motion state judging method and corresponding intelligent feeding method | |
CN1272907C (en) | Clock data recovering system with external early/late input | |
CN115590505B (en) | Data anomaly analysis method for intelligent motion monitoring device | |
CN103995742B (en) | Embedded type real-time scheduling control device and method based on MCU | |
CN102789599A (en) | Operation shop bottleneck recognition method based on cluster analysis and multiple attribute decision making | |
CN106960244A (en) | A kind of genetic algorithm and the evolution algorithm of particle cluster algorithm Parallel Fusion | |
CN103099639B (en) | Ring topological structure of positron emission tomography (PET) imaging system and achieving method thereof | |
CN104751200B (en) | A kind of method of SVM network traffic classification | |
CN104391879A (en) | Method and device for hierarchical clustering | |
CN105488134A (en) | Big data processing method and big data processing device | |
CN110533092A (en) | A kind of wind power generating set SCADA data classification method and application based on operating condition | |
CN104035901A (en) | TTCAN bus timing and data transmitting method | |
CN107220449A (en) | A kind of power of fan curve modeling method based on piecewise nonlinear function | |
CN105075886A (en) | Dairy cow automatic feeding device and corresponding intelligent feeding system | |
CN102289533B (en) | Method for managing regression test of large scale integrated (VLSI) circuit based on geometric programming | |
CN112047209B (en) | Automatic calibration method, medium, terminal and device for elevator floors | |
CN202548610U (en) | Networking control system for circular knitting machines | |
CN113529341B (en) | Method for determining the water intake of a washing device and washing device | |
CN108153260A (en) | A kind of Discrete Intelligence manufacture system control terminal based on internet | |
CN101047317A (en) | Digital synchronous indication, control method for ship power station generator | |
CN108960343A (en) | A kind of solid waste recognition methods, system, device and readable storage medium storing program for executing | |
CN106253763B (en) | The filtering method and device of encoder | |
To et al. | Analysis of cardiac imaging data using decision tree based parallel genetic programming | |
CN110516796A (en) | A kind of grouping convolution process optimization method of Embedded platform | |
CN114326590A (en) | Machine tool data acquisition and sharing device and acquisition method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171121 Termination date: 20180727 |
|
CF01 | Termination of patent right due to non-payment of annual fee |